Triple
T18217599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beverly Farms station |
E436203
|
entity |
| Predicate | lineTerminusDirection |
P3384
|
FINISHED |
| Object | Rockport |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Rockport | Statement: [Beverly Farms station, lineTerminusDirection, Rockport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rockport Context triple: [Beverly Farms station, lineTerminusDirection, Rockport]
-
A.
Rockport
chosen
Rockport is a small coastal town on Cape Ann in northeastern Massachusetts, known for its picturesque harbor, rocky shoreline, and thriving arts community.
-
B.
Jacksonport
Jacksonport is a small lakeside village on Wisconsin’s Door Peninsula known for its quiet beaches, parks, and access to Lake Michigan.
-
C.
Keyport
Keyport is a small waterfront community in Kitsap County, Washington, known for its naval undersea warfare facilities and marina on the Kitsap Peninsula.
-
D.
Rossport
Rossport is a small lakeside community in northern Ontario, Canada, known for its scenic Lake Superior shoreline and outdoor recreation opportunities.
-
E.
Cloverport
Cloverport is a small city in Breckinridge County, Kentucky, located along the Ohio River.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e4782db4819093baee57f34be490 |
completed | April 19, 2026, 2:19 p.m. |
Created at: April 10, 2026, 10:32 a.m.